gpt-realtime-2.1
gpt-realtime-2.1 updates GPT-Realtime-2 with better alphanumeric recognition, steadier silence and noise handling, and improved interruption behavior, keeping speech-to-speech interaction, configurable reasoning effort, instruction following, and tool use for complex voice-agent workflows. Your use is subject to OpenAI's Terms & Privacy Policies.
- Input and output price
- Input $4, Output $24, Per 1M tokens
import { gateway } from '@ai-sdk/gateway';
export async function POST() { const { token, url } = await gateway.experimental_realtime.getToken({ model: 'openai/gpt-realtime-2.1', });
return Response.json({ token, url, tools: [] });}Copy link to headingPlayground
Try out gpt-realtime-2.1 by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
gpt-realtime-2.1Voice agent
Talk to a realtime agent. It listens to your voice and replies with audio.
Start the session and ask the agent something.
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingMore models by OpenAI
| Model |
|---|
| 1.1M | 3.2 s | 66 tps | $10/M+2 more | $50/M+2 more | Read$1/M Write$12.50/M | $10/K | +5 |  | 09/04/2026 | |||||
| 1.1M | 2.0 s | 146 tps | $0.20/M+2 more | $1.20/M+2 more | Read$0.02/M Write$0.25/M | $10/K | +5 |  | 07/09/2026 | |||||
| 1.1M | 5.3 s | 72 tps | $4/M+2 more | $20/M+2 more | Read$0.40/M Write$5/M | $10/K | +5 | | 07/09/2026 | |||||
| 1.1M | 1.9 s | 112 tps | $2/M+2 more | $12/M+2 more | Read$0.20/M Write$2.50/M | $10/K | +5 | | 07/09/2026 | |||||
| 400K | 4.5 s | 182 tps | $0.05/M | $0.40/M | Read$0.005/M | $14/K | +3 | | 08/07/2025 | |||||
| 400K | 3.5 s | 116 tps | $0.25/M+1 more | $2/M+1 more | Read$0.03/M | $14/K | +3 | | 08/07/2025 |
Copy link to headingAbout gpt-realtime-2.1
gpt-realtime-2.1 became available on July 9, 2026 as an update to gpt-realtime-2. OpenAI improved three behaviors that decide whether a voice call succeeds: alphanumeric recognition, silence and noise handling, and interruption handling. Speech-to-speech interaction, configurable reasoning effort, instruction following, and tool use all carry over.
Alphanumeric recognition covers order numbers, account IDs, postal codes, and confirmation codes, which is where voice agents most often lose a call. Better silence and noise handling reduces false turn boundaries in loud rooms and over phone lines, so the agent talks over the caller less. Improved interruption behavior lets a caller cut in without derailing the session.
Reasoning effort stays configurable, so you decide how much thinking each session gets. Higher effort raises answer quality on complex turns and increases latency and output token usage. OpenAI also improved caching across the realtime voice models, which brings tail latency down. See the live metrics on this page for current numbers.
gpt-realtime-2.1 takes text, audio, and image input and returns text and audio, with a context window of 128K tokens and up to 32K tokens of output. Function calling works mid-conversation, so an agent can look up an order or update a record while the caller is still talking. Through AI Gateway, you get the same authentication, observability, and spend controls as your text models, with no markup on provider pricing.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Reasoning effort is the main tuning decision. Higher effort improves answers on complex turns and raises latency and output token usage, so start low for production voice agents and increase it only where your transcripts show the model struggling.
- Configuration: Realtime support on AI Gateway is in beta through AI SDK 7. The integration runs over WebSocket: your server mints a short-lived token, and the browser connects with the AI SDK's realtime hook, which handles microphone capture and playback. Your AI Gateway API key never reaches the client.
- Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use gpt-realtime-2.1
Best for
- Production Voice Agents: Support and phone workflows that need reliable instruction following and tool use
- Spoken Identifier Capture: Order numbers, account codes, and postal codes read aloud by callers
- Noisy Call Environments: Contact centers, vehicles, and public spaces where background sound is constant
- Interruption-Heavy Conversations: Callers who cut in mid-response and expect the agent to keep up
- Mixed-Difficulty Sessions: Reasoning effort tuned to match compute to the task in front of the agent
Consider alternatives when
- Live Transcription Only:
gpt-realtime-whisperstreams text from audio without a spoken reply - High-Volume Voice Features:
gpt-realtime-minicovers lightweight interactions at a lower rate - Recorded Audio Jobs:
gpt-4o-transcribeandwhisper-1transcribe files rather than live streams - Speech Generation Only:
tts-1andtts-1-hdturn written text into spoken audio
Copy link to headingConclusion
gpt-realtime-2.1 is a direct upgrade path for anything already running on GPT-Realtime-2. The gains land on spoken identifiers, noisy audio, and interruptions, which is where production voice agents fail. Start at low reasoning effort and raise it only for the turns that need it.
Copy link to headingFrequently Asked Questions
What changed between gpt-realtime-2.1 and GPT-Realtime-2?
Alphanumeric recognition, silence and noise handling, and interruption behavior all improved. Speech-to-speech interaction, configurable reasoning effort, instruction following, and tool use carry over from GPT-Realtime-2.
How do I access gpt-realtime-2.1 through AI Gateway?
Realtime support is in beta through AI SDK 7. Mint a short-lived token on your server with the AI SDK's gateway provider, then connect from the browser with the AI SDK's realtime hook over WebSocket. The hook manages microphone capture and audio playback.
How should I set reasoning effort for gpt-realtime-2.1?
Start low for production voice agents. Higher effort improves reasoning on complex turns and increases both latency and output token usage, so raise it only for the sessions or turns where transcripts show the agent struggling.
Why does alphanumeric recognition matter for a voice agent?
Order numbers, account IDs, postal codes, and confirmation codes are the details a call turns on. gpt-realtime-2.1 captures them more reliably than GPT-Realtime-2, which reduces the repeat-back loops that frustrate callers.
Can gpt-realtime-2.1 call tools during a live conversation?
Yes. Function calling works mid-conversation, so the agent can look up an order or update a record while the caller is still talking, then answer with the result.
What inputs and outputs does gpt-realtime-2.1 support?
Text, audio, and image input, with text and audio output. The context window is 128K tokens, with up to 32K tokens of output.
How is gpt-realtime-2.1 priced?
Pricing is listed on this page and covers text, audio, and image tokens separately. Rates reflect the providers routing through AI Gateway and update when those providers change list prices.
Does gpt-realtime-2.1 support zero data retention through AI Gateway?
Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
What are typical latency characteristics?
This page shows live performance metrics measured across real AI Gateway traffic. Higher reasoning effort settings add thinking time before the agent speaks.